Senior Solution Architect with Agentic AI

Technology Stack

AWS, AWS Bedrock AgentCore, LangGraph, Strands, AutoGen, CrewAI, OpenAI APIs, Large Language Models, Retrieval Augmented Generation (RAG), Python, MCP, A2A, IAM, Cedar, Open Policy Agent (OPA), observability platforms, distributed systems, Kubernetes, cloud-native architecture.

Project Overview

The project focuses on building a next-generation agentic AI platform that enables autonomous agents to collaborate, access enterprise tools, and execute complex workflows in a secure and governed environment. The solution combines advanced orchestration frameworks, LLM-powered applications, runtime controls, observability, and cloud-native infrastructure to support production-scale AI capabilities.

Team

You will work in a medium-sized team of 10–20 people with solution architects, AI engineers, platform engineers, cloud specialists, security experts, and product stakeholders. The team operates in a highly collaborative environment where architectural decisions are reviewed across multiple domains to ensure scalability, governance, and business alignment.

Position Overview

We are looking for a Senior Solution Architect with strong experience in agentic AI systems, LLM application architecture, and cloud platforms. You will define architecture standards, design scalable agent ecosystems, and guide implementation of enterprise-grade AI solutions with a focus on governance, observability, security, and operational excellence.

Responsibilities

• Develop architecture blueprints for enterprise-scale agentic AI platforms.
• Define agent orchestration patterns, multi-agent collaboration models, memory management approaches, and runtime execution strategies.
• Design agent-to-tool and agent-to-agent integration frameworks using MCP, A2A, function calling, and related protocols.
• Establish LLM application architecture standards including RAG pipelines, prompt engineering, context management, model routing, and output evaluation.
• Design governance frameworks for autonomous systems, including authorization, identity management, policy enforcement, and auditability.
• Lead architecture decisions for runtime environments, integration gateways, observability solutions, and evaluation frameworks.
• Define monitoring, tracing, quality assurance, and safety evaluation approaches for agentic systems.
• Collaborate with engineering, security, and platform teams to align architecture decisions with enterprise requirements.
• Present architecture proposals and technical strategies to architecture review boards and governance committees.
• Provide technical leadership and guidance throughout the solution lifecycle.

Requirements

• 6+ years of software architecture experience.
• 2+ years of experience architecting production-grade LLM-powered applications or agentic AI systems.
• Hands-on production experience with at least one agent orchestration framework, such as LangGraph, Strands, AutoGen, CrewAI, or an equivalent solution.
• Experience designing platform-level agent-to-tool integration layers consumed by multiple agents, products, or teams.
• Experience architecting at least two of the following domains for agentic systems: runtime and execution environments; tool and gateway integrations; identity and policy enforcement; observability and evaluation platforms.
• Experience defining architecture standards and making architecture-level technology decisions.
• Experience presenting solutions during architecture reviews, governance reviews, design boards, or equivalent forums.
• Strong understanding of cloud architecture principles, preferably within AWS environments.
• Knowledge of modern LLM application architecture, including RAG, prompt engineering, model orchestration, and evaluation methodologies.

Nice to Have

• Hands-on experience with AWS Bedrock AgentCore, including Runtime, Gateway, Registry, Policy, Evaluation, and Observability capabilities.
• Experience with policy-as-code frameworks such as Cedar or Open Policy Agent (OPA).
• Familiarity with MCP and A2A protocol specifications.
• Experience working within enterprise, regulated, or highly governed environments.
• Experience designing agent identity solutions and non-human identity federation models.
• Knowledge of agent governance, compliance, and security frameworks.
• Experience supporting large-scale AI platform initiatives across multiple business domains.

What We Offer

• Up to 26 business days of vacation per year.
• 10 fully paid illness/special days off per year for all contract types; no medical documentation required.
• Health and life insurance (Luxmed).
• MyBenefit platform with a Multisport option.
• Internal psychological support service.
• English language classes from the first working day.
• Access to O’Reilly, LinkedIn Learning, Udemy, and a broad catalog of internal training.
• Flexible workplace: office, home, or hybrid work.
• Tech Skills Mentoring Program.
• Opportunities to develop as a public speaker, mentor, or technical interviewer.
• Fully paid bench time when not assigned to a project.
• Certification reimbursement for AWS, GCP, Microsoft, and other certifications.